Model: None
Dataset: The Pile
Neuron 1945 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 8.9136. Min Range: -8.9136
Max Act: 8.9136. Min Act: -0.1700
Data Index: 2438508 (The Pile)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9136. Min Range: -8.9136
Max Act: 8.9136. Min Act: -0.1700
Data Index: 2983693 (The Pile)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9136. Min Range: -8.9136
Max Act: 8.7886. Min Act: -0.1700
Data Index: 7102477 (The Pile)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9136. Min Range: -8.9136
Max Act: 8.7886. Min Act: -0.1700
Data Index: 4653668 (The Pile)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9136. Min Range: -8.9136
Max Act: 8.7886. Min Act: -0.1700
Data Index: 9970452 (The Pile)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9136. Min Range: -8.9136
Max Act: 8.7261. Min Act: -0.1700
Data Index: 1169049 (The Pile)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9136. Min Range: -8.9136
Max Act: 8.7261. Min Act: -0.1700
Data Index: 5409876 (The Pile)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9136. Min Range: -8.9136
Max Act: 8.7261. Min Act: -0.1700
Data Index: 6627780 (The Pile)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9136. Min Range: -8.9136
Max Act: 8.7261. Min Act: -0.1700
Data Index: 9191396 (The Pile)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9136. Min Range: -8.9136
Max Act: 8.6636. Min Act: -0.1700
Data Index: 5062614 (The Pile)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9136. Min Range: -8.9136
Max Act: 8.6636. Min Act: -0.1700
Data Index: 4525500 (The Pile)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9136. Min Range: -8.9136
Max Act: 8.6636. Min Act: -0.1700
Data Index: 3372369 (The Pile)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9136. Min Range: -8.9136
Max Act: 8.6636. Min Act: -0.1700
Data Index: 10657355 (The Pile)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9136. Min Range: -8.9136
Max Act: 8.6636. Min Act: -0.1700
Data Index: 1122212 (The Pile)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9136. Min Range: -8.9136
Max Act: 8.6636. Min Act: -0.1700
Data Index: 10090957 (The Pile)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9136. Min Range: -8.9136
Max Act: 8.6636. Min Act: -0.1700
Data Index: 8182903 (The Pile)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9136. Min Range: -8.9136
Max Act: 8.6636. Min Act: -0.1700
Data Index: 7984111 (The Pile)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9136. Min Range: -8.9136
Max Act: 8.6011. Min Act: -0.1700
Data Index: 8531586 (The Pile)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9136. Min Range: -8.9136
Max Act: 8.6011. Min Act: -0.1700
Data Index: 6538509 (The Pile)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9136. Min Range: -8.9136
Max Act: 8.6011. Min Act: -0.1700
Data Index: 5855624 (The Pile)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19